EntRGi: Entropy Aware Reward Guidance for Diffusion Language Models

• URL: http://arxiv.org/abs/2602.05000v1
• Date: Wed, 04 Feb 2026 19:37:14 GMT
• Title: EntRGi: Entropy Aware Reward Guidance for Diffusion Language Models
• Authors: Atula Tejaswi, Litu Rout, Constantine Caramanis, Sanjay Shakkottai, Sujay Sanghavi,
• Abstract summary: We study reward guidance for discrete diffusion language models, where one cannot differentiate through the natural outputs of the model.<n>Existing approaches either replace discrete tokens with continuous relaxations, or employ techniques like the straight-through estimator.<n>We introduce EntRGi: Entropy aware Reward Guidance that dynamically regulates the gradients from the reward model.
• Score: 42.41157160976886
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reward guidance has been applied to great success in the test-time adaptation of continuous diffusion models; it updates each denoising step using the gradients from a downstream reward model. We study reward guidance for discrete diffusion language models, where one cannot differentiate through the natural outputs of the model because they are discrete tokens. Existing approaches either replace these discrete tokens with continuous relaxations, or employ techniques like the straight-through estimator. In this work, we show the downsides of both these methods. The former degrades gradient feedback because the reward model has never been trained with continuous inputs. The latter involves incorrect optimization because the gradient evaluated at discrete tokens is used to update continuous logits. Our key innovation is to go beyond this tradeoff by introducing a novel mechanism called EntRGi: Entropy aware Reward Guidance that dynamically regulates the gradients from the reward model. By modulating the continuous relaxation using the model's confidence, our approach substantially improves reward guidance while providing reliable inputs to the reward model. We empirically validate our approach on a 7B-parameter diffusion language model across 3 diverse reward models and 3 multi-skill benchmarks, showing consistent improvements over state-of-the-art methods.

Related papers

• Distributional value gradients for stochastic environments [37.5115685757579]
  Gradient-regularized value learning methods improve sample efficiency by leveraging learned models of transition dynamics and rewards to estimate return.<n>In this work, we address these limitations by extending distributional reinforcement learning on continuous state-action spaces.<n>Inspired by Value Gradients (SVG), our method utilizes a one-step world model of reward and transition distributions implemented via a conditional Vari Autoencoder (cVAE).
  arXiv  Detail & Related papers  (2026-01-27T21:31:07Z)
• From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model [72.73512218682187]
  We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors.<n>Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop.<n>This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade.
  arXiv  Detail & Related papers  (2025-10-22T06:58:55Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• The Diffusion Duality [24.39272541108744]
  Uniform-state diffusion processes naturally emerge from an underlying Gaussian diffusion.<n>Models trained with curriculum learning surpass autoregressive models in zero-shot perplexity on 3 of 7 benchmarks.<n>We present Discrete Consistency Distillation, which adapts consistency distillation from the continuous to the discrete setting.
  arXiv  Detail & Related papers  (2025-06-12T16:55:35Z)
• Continuous Speculative Decoding for Autoregressive Image Generation [27.308442169466975]
  Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation.<n> speculative decoding has effectively accelerated discrete autoregressive inference.<n>This work addresses challenges from low acceptance rate, inconsistent output distribution, and modified distribution without analytic expression.
  arXiv  Detail & Related papers  (2024-11-18T09:19:15Z)
• Training-free Diffusion Model Alignment with Sampling Demons [15.400553977713914]
  We propose an optimization approach, dubbed Demon, to guide the denoising process at inference time without backpropagation through reward functions or model retraining.<n>Our approach works by controlling noise distribution in denoising steps to concentrate density on regions corresponding to high rewards through optimization.<n>Our experiments show that the proposed approach significantly improves the average aesthetics scores text-to-image generation.
  arXiv  Detail & Related papers  (2024-10-08T07:33:49Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion [61.03681839276652]
  Diffusion Forcing is a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.<n>We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens.
  arXiv  Detail & Related papers  (2024-07-01T15:43:25Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.